Matches in SemOpenAlex for { <https://semopenalex.org/work/W2920691502> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2920691502 abstract "Timely and high-resolution estimates of the home locations of a sufficiently large subset of the population are critical for effective disaster response and public health intervention, but this is still an open problem. Conventional data sources, such as census and surveys, have a substantial time lag and cannot capture seasonal trends. Recently, social media data has been exploited to address this problem by leveraging its large user-base and real-time nature. However, inherent sparsity and noise, along with large estimation uncertainty in home locations, have limited their effectiveness. Consequently, much of previous research has aimed only at a coarse spatial resolution, with accuracy being limited for high-resolution methods. In this paper, we develop a deep-learning solution that uses a two-phase dynamic structure to deal with sparse and noisy social media data. In the first phase, high recall is achieved using a random forest, producing more balanced home location candidates. Then two deep neural networks are used to detect home locations with high accuracy. We obtained over 90% accuracy for large subsets on a commonly used dataset. Compared to other high-resolution methods, our approach yields up to 60% error reduction by reducing high-resolution home prediction error from over 21% to less than 8%. Systematic comparisons show that our method gives the highest accuracy both for the entire sample and for subsets. Evaluation on a real-world public health problem further validates the effectiveness of our approach." @default.
- W2920691502 created "2019-03-11" @default.
- W2920691502 creator A5025749256 @default.
- W2920691502 creator A5049983217 @default.
- W2920691502 creator A5081004875 @default.
- W2920691502 date "2019-02-03" @default.
- W2920691502 modified "2023-09-26" @default.
- W2920691502 title "High-resolution home location prediction from tweets using deep learning with dynamic structure" @default.
- W2920691502 cites W1809720746 @default.
- W2920691502 cites W1841910326 @default.
- W2920691502 cites W1994236950 @default.
- W2920691502 cites W2006239241 @default.
- W2920691502 cites W2018277822 @default.
- W2920691502 cites W2095705004 @default.
- W2920691502 cites W2104008533 @default.
- W2920691502 cites W2110953678 @default.
- W2920691502 cites W2125283600 @default.
- W2920691502 cites W2142191319 @default.
- W2920691502 cites W2151378814 @default.
- W2920691502 cites W2162301084 @default.
- W2920691502 cites W2168346693 @default.
- W2920691502 cites W2277420157 @default.
- W2920691502 cites W2282112529 @default.
- W2920691502 cites W2557283755 @default.
- W2920691502 cites W2565903393 @default.
- W2920691502 cites W2574459053 @default.
- W2920691502 cites W2576718852 @default.
- W2920691502 cites W2602684753 @default.
- W2920691502 cites W2612301670 @default.
- W2920691502 cites W2784570262 @default.
- W2920691502 cites W2806188267 @default.
- W2920691502 cites W2808494595 @default.
- W2920691502 cites W2811210701 @default.
- W2920691502 cites W2897275116 @default.
- W2920691502 cites W3147736584 @default.
- W2920691502 cites W86330731 @default.
- W2920691502 doi "https://doi.org/10.48550/arxiv.1902.03111" @default.
- W2920691502 hasPublicationYear "2019" @default.
- W2920691502 type Work @default.
- W2920691502 sameAs 2920691502 @default.
- W2920691502 citedByCount "0" @default.
- W2920691502 crossrefType "posted-content" @default.
- W2920691502 hasAuthorship W2920691502A5025749256 @default.
- W2920691502 hasAuthorship W2920691502A5049983217 @default.
- W2920691502 hasAuthorship W2920691502A5081004875 @default.
- W2920691502 hasBestOaLocation W29206915021 @default.
- W2920691502 hasConcept C108583219 @default.
- W2920691502 hasConcept C119857082 @default.
- W2920691502 hasConcept C124101348 @default.
- W2920691502 hasConcept C136764020 @default.
- W2920691502 hasConcept C144024400 @default.
- W2920691502 hasConcept C149923435 @default.
- W2920691502 hasConcept C154945302 @default.
- W2920691502 hasConcept C169258074 @default.
- W2920691502 hasConcept C2522767166 @default.
- W2920691502 hasConcept C2908647359 @default.
- W2920691502 hasConcept C41008148 @default.
- W2920691502 hasConcept C518677369 @default.
- W2920691502 hasConcept C81669768 @default.
- W2920691502 hasConceptScore W2920691502C108583219 @default.
- W2920691502 hasConceptScore W2920691502C119857082 @default.
- W2920691502 hasConceptScore W2920691502C124101348 @default.
- W2920691502 hasConceptScore W2920691502C136764020 @default.
- W2920691502 hasConceptScore W2920691502C144024400 @default.
- W2920691502 hasConceptScore W2920691502C149923435 @default.
- W2920691502 hasConceptScore W2920691502C154945302 @default.
- W2920691502 hasConceptScore W2920691502C169258074 @default.
- W2920691502 hasConceptScore W2920691502C2522767166 @default.
- W2920691502 hasConceptScore W2920691502C2908647359 @default.
- W2920691502 hasConceptScore W2920691502C41008148 @default.
- W2920691502 hasConceptScore W2920691502C518677369 @default.
- W2920691502 hasConceptScore W2920691502C81669768 @default.
- W2920691502 hasLocation W29206915021 @default.
- W2920691502 hasOpenAccess W2920691502 @default.
- W2920691502 hasPrimaryLocation W29206915021 @default.
- W2920691502 hasRelatedWork W2968586400 @default.
- W2920691502 hasRelatedWork W3211546796 @default.
- W2920691502 hasRelatedWork W4223564025 @default.
- W2920691502 hasRelatedWork W4223943233 @default.
- W2920691502 hasRelatedWork W4281616679 @default.
- W2920691502 hasRelatedWork W4312200629 @default.
- W2920691502 hasRelatedWork W4360585206 @default.
- W2920691502 hasRelatedWork W4364306694 @default.
- W2920691502 hasRelatedWork W4380075502 @default.
- W2920691502 hasRelatedWork W4380086463 @default.
- W2920691502 isParatext "false" @default.
- W2920691502 isRetracted "false" @default.
- W2920691502 magId "2920691502" @default.
- W2920691502 workType "article" @default.